CN117876374A - Metal slurry wiring hole filling and monitoring method for HTCC ceramic - Google Patents
Metal slurry wiring hole filling and monitoring method for HTCC ceramic Download PDFInfo
- Publication number
- CN117876374A CN117876374A CN202410281539.2A CN202410281539A CN117876374A CN 117876374 A CN117876374 A CN 117876374A CN 202410281539 A CN202410281539 A CN 202410281539A CN 117876374 A CN117876374 A CN 117876374A
- Authority
- CN
- China
- Prior art keywords
- pixel point
- value
- degree
- gray
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000000919 ceramic Substances 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000002184 metal Substances 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- SWPMTVXRLXPNDP-UHFFFAOYSA-N 4-hydroxy-2,6,6-trimethylcyclohexene-1-carbaldehyde Chemical compound CC1=C(C=O)C(C)(C)CC(O)C1 SWPMTVXRLXPNDP-UHFFFAOYSA-N 0.000 title claims abstract 14
- 239000002002 slurry Substances 0.000 title description 9
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000007547 defect Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 230000002950 deficient Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a metal paste wiring hole filling and monitoring method for HTCC ceramics, which comprises the following steps: obtaining a hole filling area gray level image of a hole filling on the HTCC ceramic, and obtaining the turbulence degree of each pixel point in each direction in the hole filling area gray level image so as to obtain the first turbulence degree of each pixel point, thereby obtaining the second turbulence degree of each pixel point, and adjusting the gray level value of the pixel point processed by a histogram equalization algorithm to obtain an enhanced image of the hole filling area gray level image so as to judge whether the hole filling quality in the hole filling area gray level image is qualified. According to the invention, the gray value of the pixel point after histogram equalization is adjusted through the second disorder degree of the self-adaptive pixel point, so that the enhancement effect of the image is improved, and the accuracy of judging whether the filling quality is qualified or not by using the enhancement image is improved.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a metal paste wiring hole filling and monitoring method for HTCC ceramics.
Background
HTCC (high temperature cofired ceramic) plays a key role in the manufacture of high performance circuits and devices as an important material in the electronics industry. HTCC ceramics are often used to make dense wiring, hole filling, etc. structures, and wiring hole filling of metal paste is one of the important links in the manufacturing process. Therefore, how to effectively realize high-quality preparation and monitoring of metal paste wiring hole filling in HTCC ceramic plays a vital role in HTCC ceramic, and the analysis of metal paste wiring hole filling is that the image is enhanced by histogram equalization so as to facilitate the follow-up research.
The existing problems are as follows: after the metal slurry wiring of the HTCC ceramic is filled, the filling is possibly uneven due to uneven slurry properties, poor substrate surface treatment and the like, and because the metal slurry wiring filling area of the HTCC ceramic has complex structure and tiny characteristics, local details can be lost when the image is directly enhanced through histogram equalization, and the accuracy of analysis of the uniformity degree of the filling area is reduced, so that the accuracy of metal slurry wiring filling and monitoring of the HTCC ceramic is reduced.
Disclosure of Invention
The invention provides a metal paste wiring hole filling and monitoring method for HTCC ceramics, which aims to solve the existing problems.
The metal slurry wiring hole filling and monitoring method for HTCC ceramics adopts the following technical scheme:
one embodiment of the invention provides a metal paste wiring hole filling and monitoring method for HTCC ceramics, which comprises the following steps:
acquiring a hole filling area gray image of a hole filling on the HTCC ceramic; in the gray level image of the hole filling area, according to the gray level value difference of each pixel point in each direction, obtaining the disorder degree of each pixel point in each direction;
obtaining a first disorder degree adjustment value and a judgment threshold value of each pixel point according to the disorder degree of each pixel point in all directions; obtaining the first disorder degree of each pixel point according to the first disorder degree adjustment value and the judgment threshold value of each pixel point;
obtaining a second disorder degree adjustment value of each pixel point according to the difference of the first disorder degree of the pixel point of each pixel point in each direction; obtaining a second disorder degree of each pixel point according to the first disorder degree and the second disorder degree adjustment value of each pixel point;
according to the second disorder degree of each pixel point, the gray value of the pixel point processed by the histogram equalization algorithm is adjusted, and an enhanced image of the gray image of the hole filling area is obtained; and judging whether the filling quality in the gray level image of the filling area is qualified or not according to the enhanced image.
Further, in the hole filling area gray level image, according to the pixel point gray level value difference of each pixel point in each direction, the turbulence degree of each pixel point in each direction is obtained, which comprises the following specific steps:
in the gray level image of the filling area, the first stepThe pixel points are used as the center, and the size is constructed as +.>Is a sliding window of (2); said->The side length of the sliding window is preset;
the horizontal direction is 0 degree to the right, and the anticlockwise rotation is respectively carried out to obtain directions corresponding to 0 degree, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees and 315 degrees;
according to the sliding window inner slave positionStarting at pixel point +.>The ratio of gray values of pixel points at different intervals in each direction is respectively obtained from the +.>Starting at pixel point +.>Average gray scale ratio of pixel points at different intervals in each direction;
according to the sliding window inner slave positionStarting at pixel point +.>Average gray scale ratio of pixel points with different intervals in each direction and gray scale value difference of the pixel points are obtained to obtain the (th)>The pixel point is at the +.>Degree of disorder in individual directions.
Further, the sliding window is internally provided with a third sliding windowStarting at pixel point +.>The ratio of gray values of pixel points at different intervals in each direction is respectively obtained from the +.>Starting at pixel point +.>The average gray scale ratio of pixel points with different intervals in each direction comprises the following specific steps:
from the first in the sliding windowStarting at the pixel point along the +.>Direction, calculate->Gray value and +.>The ratio of gray values of each pixel point is recorded as the average value of the ratio of gray values of all adjacent pixel points from the +.>Starting at pixel point +.>Average gray scale ratio of adjacent pixel points in individual direction +.>The method comprises the steps of carrying out a first treatment on the surface of the Calculate->Gray value of each pixel pointRatio of gray values of each pixel, all intervals are +.>The average value of the ratio of the gray values of the pixels of (2) is recorded as the value from +.>Starting at pixel point +.>The interval in the individual direction is +.>The average gray ratio of the pixels of (2)>The method comprises the steps of carrying out a first treatment on the surface of the Said->Is a pre-preparationA first interval is set;
according toThe acquisition mode of (1) is obtained from the +.>Starting at pixel point +.>Spaced in each direction asThe average gray ratio of the pixels of (2)>From the +.>Starting at pixel point +.>The interval in the individual direction is +.>The average gray ratio of the pixels of (2)>The method comprises the steps of carrying out a first treatment on the surface of the Said->Is a preset second interval; said->Is a preset third interval.
Further, the sliding window is internally provided with a third sliding windowStarting at pixel point +.>Average gray scale ratio of pixel points at different intervals in each directionAnd the gray value difference of the pixel points to obtain the +.>The pixel point is at the +.>The degree of disorder in each direction comprises the following specific steps:
calculating the inside slave of the sliding windowStarting at pixel point +.>The absolute value of the difference value between the first pixel point and the gray values of all other pixel points in each direction is recorded as the average value of the absolute value of the difference value between the first pixel point and the gray values of all other pixel points in each direction, and the average value is recorded as the first value in the sliding window>The pixel point is at the +.>Gray scale differences in the individual directions;
will be、/>、/>And +.>The minimum value of (2) is marked as +.>The pixel point is at the +.>Gray scale variation fluctuation stability in the individual directions; wherein (1)>As a function of absolute value;
calculating the inside slave of the sliding windowStarting at pixel point +.>Normalized value of standard deviation of gray values of all pixels in each direction, the first +.>The pixel point is at the +.>Gray scale difference in individual direction, gray scale variation fluctuation stability, and product of normalized values of the standard deviation, denoted as +.>The pixel point is at the +.>Degree of disorder in individual directions.
Further, according to the degree of disorder of each pixel point in all directions, a first disorder degree adjustment value and a judgment threshold value of each pixel point are obtained, and the method comprises the following specific steps:
calculate the firstThe average value of the disorder degree of each pixel point in all directions is recorded as a judgment threshold value;
in the first placeIn all directions of the pixel points, the direction of the disorder degree larger than or equal to the judgment threshold value is marked as the +.>A main direction of the individual pixel points; will be disturbedThe direction in which the degree is smaller than the judgment threshold is denoted as +.>The sub-directions of the pixel points;
calculating judgment threshold values respectively with the firstAbsolute values of the difference values of the disturbance degrees of the pixel points in all main directions are recorded as products of the average values of the absolute values of the difference values of the disturbance degrees in all main directions and preset expansion coefficientsThe adjustment values of the pixel points in the main direction;
calculating judgment threshold values respectively with the firstAbsolute value of difference of degree of disorder of each pixel point in all directions, and the average value of absolute value of difference of degree of disorder in all directions is recorded as +.>Adjusting values of the pixel points in the direction;
will be the firstThe adjustment value of the individual pixel point in the main direction and +.>The sum of the adjustment values of the individual pixels in the direction is denoted by +.>And a first disturbance degree adjustment value of each pixel point.
Further, the step of obtaining the first disorder degree of each pixel point according to the first disorder degree adjustment value and the judgment threshold value of each pixel point includes the following specific steps:
calculate the firstThe product of the first disorder degree adjustment value and the judgment threshold value of each pixel point is recorded as the normalized value of the product +.>A first degree of disorder of the individual pixels.
Further, the step of obtaining the second disturbance degree adjustment value of each pixel point according to the difference of the first disturbance degree of the pixel point of each pixel point in each direction comprises the following specific steps:
calculating the inside slave of the sliding windowStarting at pixel point +.>Absolute values of differences of first disorder degree between first pixel point and other pixel points in each direction, respectively, and adding the +.>The average value of the absolute values of the difference values of the first pixel point and the first disorder degree of all other pixel points in each direction is marked as +.>The pixel point is at the +.>Adjustment values in the individual directions;
will be the firstThe average value of the adjustment values of the individual pixels in all directions is denoted by +.>And a second disturbance degree adjustment value of each pixel point.
Further, the step of obtaining the second disorder degree of each pixel point according to the first disorder degree and the second disorder degree adjustment value of each pixel point comprises the following specific steps:
calculate the firstSecond disorder degree adjustment value and +.>The product of the first disorder degree of each pixel point is recorded as the normalized value of the product +.>And a second degree of disorder of each pixel.
Further, the step of adjusting the gray value of the pixel point processed by the histogram equalization algorithm according to the second disorder degree of each pixel point to obtain an enhanced image of the gray image of the hole filling area comprises the following specific steps:
performing histogram equalization processing on the gray level image of the hole filling area by using a histogram equalization algorithm to obtain a gray level value of each pixel point in the gray level image of the hole filling area after histogram equalization;
calculate the firstGray value and +.>The product of the second degree of disorder of each pixel is marked as the +.>Enhanced gray values of the individual pixels;
in the hole filling area gray level image, an image formed by the enhanced gray level values of all the pixel points is recorded as an enhanced image of the hole filling area gray level image.
Further, the step of judging whether the filling quality in the gray level image of the filling area is qualified according to the enhanced image comprises the following specific steps:
dividing a defective region in the enhanced image by using the trained divided neural network, and judging that the filling quality in the gray level image of the filling region is unqualified when the defective region exists; and when the defect area does not exist, judging that the filling quality in the gray level image of the filling area is qualified.
The technical scheme of the invention has the beneficial effects that:
in the embodiment of the invention, a hole filling area gray level image of a hole filling on HTCC ceramic is obtained, and in the hole filling area gray level image, the turbulence degree of each pixel point in each direction is obtained, so that the first turbulence degree of each pixel point is obtained, and the first turbulence degree is calculated as a parameter for subsequently adjusting gray level values according to the gray level difference of the pixel point in each direction in a local area, so that local details can be better reserved while the image contrast is enhanced subsequently. The second disorder degree of each pixel point is obtained and is used for adjusting the gray value of the pixel point processed by a histogram equalization algorithm to obtain an enhanced image of the gray image of the hole filling area, the uniformity degree of the distribution of the pixel points in a local range is determined by analyzing the characteristic expression of each pixel point in the local area, namely the first disorder degree, the necessity of enhancement of the pixel points in the local area is determined, namely the second disorder degree, so that the contrast between each pixel point in the enhanced image is more obvious, the texture detail is better reserved, the image enhancement effect is improved, and the monitoring effect of the metal paste wiring hole filling of the HTCC ceramic is improved. And judging whether the filling quality in the gray level image of the filling area is qualified or not according to the enhanced image. The invention adjusts the gray value of the pixel point after the histogram equalization through the second disorder degree of the self-adaptive pixel point, and improves the enhancement effect of the image, thereby improving the accuracy of judging whether the filling quality is qualified or not by using the enhancement image.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a metal paste routing pore-filling and monitoring method for HTCC ceramics according to the present invention;
fig. 2 is a schematic diagram of an acquisition flow of a hole filling quality detection result according to the present embodiment.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following description refers to the specific implementation, structure, characteristics and effects of a metal paste wiring hole filling and monitoring method for HTCC ceramic according to the present invention, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of a metal paste wiring hole filling and monitoring method for HTCC ceramics with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a metal paste wiring hole filling and monitoring method for HTCC ceramic according to an embodiment of the present invention is shown, and the method includes the following steps:
step S001: acquiring a hole filling area gray image of a hole filling on the HTCC ceramic; in the gray level image of the hole filling area, the turbulence degree of each pixel point in each direction is obtained according to the gray level value difference of the pixel point in each direction.
The main purpose of the embodiment of the invention is to determine the enhancement necessity according to the characteristic performance of each pixel point in a certain range in a local area of an image aiming at the problem that the uniformity of the HTCC ceramic wiring hole filling image is not easy to analyze, so that the self-adaptive histogram equalization is carried out, the image contrast is improved, and meanwhile, the texture information details of the HTCC ceramic wiring hole filling image are kept, so that the efficiency of metal slurry wiring hole filling and monitoring of the HTCC ceramic is improved.
And shooting metal paste wiring hole filling areas of the HTCC ceramic one by using a scanning electron microscope to obtain a plurality of hole filling area images, namely, each hole filling on the HTCC ceramic corresponds to one image, and carrying out graying treatment on each hole filling area image to obtain a hole filling area gray image. Wherein, the Chinese name of HTCC is high-temperature co-fired Ceramic, and English is High Temperature Co-natural Ceramic. The image graying process is a well-known technique, and a specific method is not described here.
Knowing that the uniformity of each hole filling area after being treated by the metal paste is different, the embodiment specifically analyzes each hole filling area, and determines the first turbulence degree of each pixel point in a local area through different performances of the contrast gray scale difference in the local area corresponding to each pixel point in each area. However, the analysis is not perfect enough, and the local area is not completely and finely compared, so that the first disturbance degree between adjacent points is compared, and the second disturbance degree is adjusted and determined. Finally, the gray level image of each hole filling area is enhanced.
In this embodiment, taking a gray scale image of any one hole filling area as an example, it is known that in the hole filling area, the hole filling area may have uneven thickness and density distribution due to uneven material properties of metal slurry, which may make signal transmission paths inconsistent, and signal transmission or electrical performance in a circuit may be unstable. Therefore, in this embodiment, each sliding window area is considered as a local area in the hole filling area, and the uniform performance of each pixel point in the sliding window area in the local area is analyzed, if the uniform performance of the current pixel point in the current local area is lower, it is indicated that the difference between the overall characteristics of the current pixel point and the local area is large, and it is indicated that the current pixel point may contain detail change information, and the distribution uniformity of the metal paste can be more reflected, so the necessity for enhancing the same is greater.
Sliding window side length preset in this embodiment9, pre-runFirst interval->Preset second interval->Preset third interval->By way of example, other values may be provided in other embodiments, which are not limited, wherein the number of intervals is selected according to the size of the sliding window side length, in this embodiment +.>In the sliding window, the maximum interval is 4 when the number of pixels in each direction from the center of the sliding window is 5.
In an exemplary filled-in region gray scale image, the following is adoptedFor example, the pixel is +.>The pixel points are used as the center, and the size is constructed as +.>Is the sliding window of +.>Local areas corresponding to the pixel points. In the local area corresponding to the pixel point, the comparison performance of each pixel point in the eight neighborhood directions of the pixel point and the pixel point analyzed at present can be analyzed, and the characteristic performance degree in the eight neighborhood directions of the pixel point analyzed at present can be determined.
In this embodiment, the eight directions corresponding to 0 degree, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees, 315 degrees are obtained by rotating the device counterclockwise with respect to the horizontal direction to the right of 0 degree, which is described as an example, and other values may be set in other embodiments, which is not limited to this embodiment.
In the first placeThe direction is exemplified by->The pixel point is at the +.>The calculation formula of the degree of disorder in each direction is:
wherein the method comprises the steps ofIs->The pixel point is at the +.>Degree of disorder in individual directions, +.>Is from the first part in the sliding window>Individual pixel pointsBeginning, at->Standard deviation of gray values of all pixels in individual directions +.>Is from the first part in the sliding window>Starting at pixel point +.>The number of all pixels in the individual direction, +.>、/>、/>、/>、/>And +.>From within the sliding window->Starting at pixel point +.>1 st, 1 st->Person, th->Person, th->Person, th->Person and->Gray value of each pixel, +.>Is from the first part in the sliding window>Starting at pixel point +.>Average gray scale ratio of adjacent pixels in the individual direction,/->Is from the first part in the sliding window>Starting at pixel point +.>The interval in the individual direction is +.>Average gray ratio of pixels of +.>Is from the first part in the sliding window>Starting at pixel point +.>The interval in the individual direction is +.>Average gray ratio of pixels of +.>Is from the first part in the sliding window>Starting at pixel point +.>The interval in the individual direction is +.>Average gray ratio of pixels of +.>For a preset first interval, +.>For a preset second interval, +.>For a preset third interval, +.>Normalizing the data values to +.>Within the section (I)>Is->、/>、/>And +.>Minimum value of->As a function of absolute value.
What needs to be described is: the sliding window is according to the firstThe pixel points are used as the center, and the size is constructed as +.>Is (are) sliding window>The larger the pixel gray value variation fluctuation in this direction, the larger the disturbance. />Indicating the%>The pixel point is at the +.>Gray scale difference in the individual directions, i.e.>The pixel point and the pixel point are at the +.>The larger the gradation difference is, the more disturbed is the average value of the absolute values of the differences of the gradation values of the other pixel points in the individual directions. />、/>、/>And +.>The average gray scale ratio of the pixel points at different intervals is shown, the different intervals represent different periods, when the average gray scale ratio is closer to 1, the gray scale values of the pixel points are the same in the periods, and the gray scale variation in the periods fluctuatesIs periodic fluctuation, i.e. fluctuation is stable. Thus take out、/>、/>And +.>The minimum value of (2) represents the +.>The pixel point is at the +.>The larger the gray-scale variation fluctuation stability in the individual direction, i.e., the minimum value, the more unstable, i.e., the more disturbed. Thus use->、And +.>Is the product of->The pixel point is at the +.>Degree of disorder in individual directions.
According to the mode, the disturbance degree of each pixel point in the gray level image of the hole filling area in each direction is obtained.
Step S002: and obtaining the first disorder degree of each pixel point according to the difference between the disorder degrees of each pixel point in all directions.
Therefore, the first pixel point can be obtained according to the disorder degree of each pixel point in all directionsA degree of disorder. Still according to the firstFor example, the +.>The average value of the degree of disorder of each pixel in eight directions is recorded as a judgment threshold value.
In the first placeThe eight directions of each pixel point are marked as the +.>The main direction of each pixel point is marked as the +.>The directions of the individual pixels.
Then the firstThe calculation formula of the first disorder degree of each pixel point is as follows:
wherein the method comprises the steps ofIs->First degree of disorder of each pixel, < >>Is->Mean value of degree of disorder of individual pixels in all directions, +.>Also is a judgment threshold value, ">Is->The pixel point is at the +.>Degree of disorder in the main direction, +.>Is->The number of main directions of the individual pixels, < >>Is->The pixel point is at the +.>Degree of disorder in the individual directions, +.>Is->The number of sub-directions of the individual pixels, < >>As absolute function>For a preset expansion coefficient +.>Normalizing the data values to +.>Interval ofAnd (3) inner part. In this embodiment +.>2, this is described as an example, and other values may be set in other embodiments, and the present example is not limited thereto.
What needs to be described is: when (when)The greater the instruction +.>The total degree of disorder of the individual pixels in all directions is large and when +.>And->When larger, say +.>The degree of disorder of the individual pixels in each direction is largely different, i.e. +.>The first disorder degree of each pixel point is larger, and as the image enhancement needs to pay more attention to the detail information in the image, the direction with larger disorder degree, namely the main direction, needs to pay more attention to the detail information in the image, and therefore the preset expansion coefficient +.>For->Make adjustments, and/or>Indicate->Adjustment value of individual pixels in main direction,/->Indicate->The adjustment value of each pixel point in the direction of division, therefore +.>Indicate->A first disturbance variable of each pixel, thereby using->And->Is the normalized value of (1), representing the firstA first degree of disorder of the individual pixels.
According to the mode, the first disorder degree of each pixel point in the gray level image of the hole filling area is obtained.
Step S003: and obtaining a second disorder degree of each pixel point according to the difference of the first disorder degree of the pixel point of each pixel point in each direction.
In this case, the first degree of disorder of each pixel point based on the local area is analyzed as one feature information of each pixel point, but in the analysis of the local area, only the analysis of the gray value difference in the eight neighborhood direction with each pixel point as the core is performed, and not the complete comparison of each pixel point in the local area, so the present embodiment also needs to compare the gray values between the adjacent pixel points, where the adjacent pixel point comparison refers to the comparison of the first degree of disorder of the adjacent pixel points, because the local area corresponding to each pixel point is approximately the same but not exactly the same. Meanwhile, each pixel point in the eight adjacent domain directions of the adjacent points is not the same, and the pixel points in the directions of different degrees are crossed. Therefore, through the comparison of the first disturbance degrees between the adjacent pixel points, other pixel points in other directions which do not participate in analysis exist in the local area of the pixel points just can be made up, and the method is equivalent to multi-direction expansion type analysis and judgment based on the first disturbance degrees of the adjacent pixel points, and improves the first disturbance degrees of all the pixel points.
Still according to the firstFor example, the pixel is +.>The calculation formula of the second disorder degree of each pixel point is as follows:
wherein the method comprises the steps ofIs->Second degree of disorder of individual pixels, < >>The number of directions is 8, < >>Is->First degree of disorder of each pixel, < >>Is from the first part in the sliding window>Starting at pixel point +.>The number of all pixels in the individual direction, +.>Is from the first part in the sliding window>Starting at pixel point +.>The (th) in the individual direction>First degree of disorder of each pixel, < >>As absolute function>Normalizing the data values to +.>Within the interval.
What needs to be described is: the sliding window is according to the firstThe pixel points are used as the center, and the size is constructed as +.>Is a sliding window of (a).Is->The pixel point is at the +.>Adjustment values in each direction, thereforeIndicate->A second disorder degree adjustment value of the pixel points, which represents the +.>The mean value of the first disorder difference of the pixel points of each pixel point in all directions is taken as +.>When the average value of the first disorder degree differences is larger, it is indicated that the first disorder degree of the pixel points in the sliding window is different, that is, the uniformity of the metal paste in the sliding window is worse, more gray level changes are contained, so +_ needs to be given>A greater weight, thereby using +.>Andnormalized value of the product of (2) representing +.>Second degree of disorder of individual pixels, < >>The larger the->The more important the individual pixels are.
Step S004: according to the second disorder degree of each pixel point, the gray value of the pixel point processed by the histogram equalization algorithm is adjusted, and an enhanced image of the gray image of the hole filling area is obtained; and judging whether the filling quality in the gray level image of the filling area is qualified or not according to the enhanced image.
From the above analysis, it is found that the second degree of disorder represents the necessity of enhancement of each pixel in a local area, and that the greater the second degree of disorder, the greater the necessity of enhancement.
And carrying out histogram equalization processing on the gray level image of the hole filling area by using a histogram equalization algorithm to obtain a gray level value of each pixel point in the gray level image of the hole filling area after histogram equalization. The histogram equalization algorithm is a well-known technique, and a specific method is not described herein.
Still according to the firstFor example, the pixel is +.>The calculation formula of the enhanced gray value of each pixel point is as follows:
wherein the method comprises the steps ofIs->Enhanced gray value of individual pixel, +.>Is->Gray value of each pixel after histogram equalization,/-for each pixel>Is->Second degree of disorder of individual pixels, < >>As a round-up function.
According to the mode, the enhanced gray value of each pixel point in the gray image of the hole filling area is obtained.
In the hole filling area gray level image, an image formed by the enhanced gray level values of all the pixel points is recorded as an enhanced image of the hole filling area gray level image.
The embodiment of the invention adopts a segmentation neural network to identify the defect area in the segmentation enhanced image.
The relevant content of the segmented neural network is as follows:
the split neural network used in the embodiment is a Mask R-CNN neural network; the data set used is an enhanced image data set. Wherein Mask R-CNN is a known technology, and the specific method is not described herein. The Chinese language of Mask R-CNN is called Mask regional convolutional neural network, and the English language is called Mask Region-based Convolutional Neural Network.
The pixel points to be segmented are divided into 2 classes, namely, the labeling process of the corresponding label of the training set is as follows: and the single-channel semantic label is marked as 0 in the normal region corresponding to the pixel point at the position, and is marked as 1 in the defect region.
The task of the network is classification, so the loss function used is a cross entropy loss function.
The defect area in the enhanced image is obtained by dividing the neural network, which is a known technique, and the specific method is not described here.
What needs to be described is: the HTCC ceramic has uneven metal paste wiring hole filling, which may generate defects such as pits, bumps, cracks, etc., and in this embodiment, the trained split neural network is used to identify the split pit, bump, crack defect areas.
And when a defect area exists in the enhanced image, judging that the filling quality in the gray level image of the filling area is unqualified. And when the defect area does not exist in the enhanced image, judging that the filling quality in the gray level image of the filling area is qualified. Fig. 2 is a schematic diagram of an acquisition flow of a hole filling quality detection result according to the present embodiment.
According to the mode, whether the filling quality of each filling hole on the HTCC ceramic is qualified or not is judged, and therefore monitoring and detection of metal paste wiring filling holes of the HTCC ceramic are completed.
The present invention has been completed.
In summary, in the embodiment of the present invention, a hole filling area gray level image of a hole filling on HTCC ceramic is obtained, in the hole filling area gray level image, according to the difference of pixel gray levels of each pixel in each direction, the turbulence degree of each pixel in each direction is obtained, according to the difference between the turbulence degrees of each pixel in all directions, the first turbulence degree of each pixel is obtained, according to the difference of the first turbulence degrees of each pixel in each direction, the second turbulence degree of each pixel is obtained, according to the second turbulence degree of each pixel, the pixel gray level processed by the histogram equalization algorithm is adjusted, so as to obtain an enhanced image of the hole filling area gray level image, and according to the enhanced image, whether the hole filling quality in the hole filling area gray level image is qualified is judged. According to the invention, the gray value of the pixel point after histogram equalization is adjusted through the second disorder degree of the self-adaptive pixel point, so that the enhancement effect of the image is improved, and the accuracy of judging whether the filling quality is qualified or not by using the enhancement image is improved.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A metal paste wiring hole filling and monitoring method for HTCC ceramics is characterized by comprising the following steps:
acquiring a hole filling area gray image of a hole filling on the HTCC ceramic; in the gray level image of the hole filling area, according to the gray level value difference of each pixel point in each direction, obtaining the disorder degree of each pixel point in each direction;
obtaining a first disorder degree adjustment value and a judgment threshold value of each pixel point according to the disorder degree of each pixel point in all directions; obtaining the first disorder degree of each pixel point according to the first disorder degree adjustment value and the judgment threshold value of each pixel point;
obtaining a second disorder degree adjustment value of each pixel point according to the difference of the first disorder degree of the pixel point of each pixel point in each direction; obtaining a second disorder degree of each pixel point according to the first disorder degree and the second disorder degree adjustment value of each pixel point;
according to the second disorder degree of each pixel point, the gray value of the pixel point processed by the histogram equalization algorithm is adjusted, and an enhanced image of the gray image of the hole filling area is obtained; and judging whether the filling quality in the gray level image of the filling area is qualified or not according to the enhanced image.
2. The method for metal paste wiring hole filling and monitoring for HTCC ceramic according to claim 1, wherein the step of obtaining the turbulence degree of each pixel point in each direction according to the pixel point gray value difference of each pixel point in each direction in the hole filling area gray image comprises the following specific steps:
in the gray level image of the filling area, the first stepThe pixel points are used as the center, and the size is constructed as +.>Is a sliding window of (2); said->The side length of the sliding window is preset;
the horizontal direction is 0 degree to the right, and the anticlockwise rotation is respectively carried out to obtain directions corresponding to 0 degree, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees and 315 degrees;
according to the sliding window inner slave positionStarting at pixel point +.>The ratio of gray values of pixel points at different intervals in each direction is respectively obtained from the +.>Starting at pixel point +.>Average gray scale ratio of pixel points at different intervals in each direction;
according to the sliding window inner slave positionStarting at pixel point +.>Average gray scale ratio of pixel points with different intervals in each direction and gray scale value difference of the pixel points are obtained to obtain the (th)>The pixel point is at the +.>Degree of disorder in individual directions.
3. The metal paste wiring hole filling and monitoring method for HTCC ceramic according to claim 2, wherein the metal paste wiring hole filling and monitoring method is characterized in thatStarting at pixel point +.>The ratio of gray values of pixel points at different intervals in each direction is respectively obtained from the +.>Starting at pixel point +.>The average gray scale ratio of pixel points with different intervals in each direction comprises the following specific steps:
from the first in the sliding windowStarting at the pixel point along the +.>Direction, calculate->Gray value and +.>The ratio of gray values of each pixel point is recorded as the average value of the ratio of gray values of all adjacent pixel points from the +.>Starting at pixel point +.>Average gray scale ratio of adjacent pixel points in individual direction +.>The method comprises the steps of carrying out a first treatment on the surface of the Calculate->Gray value and +.>Ratio of gray values of each pixel, all intervals are +.>The average value of the ratio of the gray values of the pixels of (2) is recorded as the value from +.>Starting at pixel point +.>The interval in the individual direction is +.>The average gray ratio of the pixels of (2)>The method comprises the steps of carrying out a first treatment on the surface of the Said->Is a preset first interval;
according toThe acquisition mode of (1) is obtained from the +.>Starting at pixel point +.>The interval in the individual direction is +.>The average gray ratio of the pixels of (2)>From the +.>Starting at pixel point +.>The interval in the individual direction is +.>The average gray ratio of the pixels of (2)>The method comprises the steps of carrying out a first treatment on the surface of the Said->Is a preset second interval; said->Is a preset third interval.
4. The metal paste wiring hole filling and monitoring method for HTCC ceramic according to claim 3, wherein the metal paste wiring hole filling and monitoring method is characterized in thatStarting at pixel point +.>Average gray scale ratio of pixel points with different intervals in each direction and gray scale value difference of the pixel points are obtained to obtain the (th)>The pixel point is at the +.>The degree of disorder in each direction comprises the following specific steps:
calculating the inside slave of the sliding windowStarting at pixel point +.>The absolute value of the difference value between the first pixel point and the gray values of all other pixel points in each direction is recorded as the average value of the absolute value of the difference value between the first pixel point and the gray values of all other pixel points in each direction, and the average value is recorded as the first value in the sliding window>The pixel point is at the +.>Gray scale differences in the individual directions;
will be、/>、/>And +.>The minimum value of (2) is marked as +.>The pixel point is at the +.>Gray scale variation fluctuation stability in the individual directions; wherein (1)>As a function of absolute value;
calculating the inside slave of the sliding windowStarting at pixel point +.>Normalized value of standard deviation of gray values of all pixels in each direction, the first +.>The pixel point is at the +.>Gray scale difference in individual direction, gray scale variation fluctuation stability, and product of normalized values of the standard deviation, denoted as +.>The pixel point is at the +.>Degree of disorder in individual directions.
5. The method for metal paste wiring hole filling and monitoring for HTCC ceramic according to claim 1, wherein the step of obtaining the first turbulence degree adjustment value and the judgment threshold value of each pixel point according to the turbulence degree of each pixel point in all directions comprises the following specific steps:
calculate the firstThe average value of the disorder degree of each pixel point in all directions is recorded as a judgment threshold value;
in the first placeIn all directions of the pixel points, the direction of the disorder degree larger than or equal to the judgment threshold value is marked as the +.>A main direction of the individual pixel points; the direction in which the disturbance degree is smaller than the judgment threshold value is denoted as +.>The sub-directions of the pixel points;
calculating judgment threshold values respectively with the firstAbsolute values of the difference values of the disturbance degrees of the individual pixel points in all main directions, and the product of the average value of the absolute values of the difference values of the disturbance degrees in all main directions and a preset expansion coefficient is recorded as the +.>The adjustment values of the pixel points in the main direction;
calculating judgment threshold values respectively with the firstAbsolute value of difference of degree of disorder of each pixel point in all directions, and the average value of absolute value of difference of degree of disorder in all directions is recorded as +.>Adjusting values of the pixel points in the direction;
will be the firstThe adjustment value of the individual pixel point in the main direction and +.>The sum of the adjustment values of the individual pixels in the direction is denoted by +.>And a first disturbance degree adjustment value of each pixel point.
6. The method for metal paste wiring hole filling and monitoring for HTCC ceramic according to claim 1, wherein the step of obtaining the first turbulence degree of each pixel according to the first turbulence degree adjustment value and the judgment threshold value of each pixel comprises the following specific steps:
calculate the firstThe product of the first disorder degree adjustment value and the judgment threshold value of each pixel point is recorded as the normalized value of the product +.>A first degree of disorder of the individual pixels.
7. The method for metal paste wiring hole filling and monitoring for HTCC ceramic according to claim 2, wherein the obtaining the second turbulence adjustment value of each pixel point according to the difference of the first turbulence of each pixel point in each direction comprises the following specific steps:
calculating the inside slave of the sliding windowStarting at pixel point +.>Absolute values of differences of first disorder degree between first pixel point and other pixel points in each direction, respectively, and adding the +.>The average value of the absolute values of the difference values of the first pixel point and the first disorder degree of all other pixel points in each direction is marked as +.>The pixel point is at the +.>Adjustment values in the individual directions;
will be the firstThe average value of the adjustment values of the individual pixels in all directions is denoted by +.>And a second disturbance degree adjustment value of each pixel point.
8. The method for metal paste wiring hole filling and monitoring for HTCC ceramic according to claim 1, wherein the obtaining the second turbulence degree of each pixel point according to the first turbulence degree and the second turbulence degree adjustment value of each pixel point comprises the following specific steps:
calculate the firstSecond disorder degree adjustment value and +.>The product of the first disorder degree of each pixel point is recorded as the normalized value of the product +.>And a second degree of disorder of each pixel.
9. The method for metal paste wiring hole filling and monitoring for HTCC ceramic according to claim 1, wherein the step of adjusting the gray value of each pixel point processed by the histogram equalization algorithm according to the second turbulence of each pixel point to obtain an enhanced image of the gray image of the hole filling area comprises the following specific steps:
performing histogram equalization processing on the gray level image of the hole filling area by using a histogram equalization algorithm to obtain a gray level value of each pixel point in the gray level image of the hole filling area after histogram equalization;
calculate the firstGray value and +.>The product of the second degree of disorder of each pixel is marked as the +.>Enhanced gray values of the individual pixels;
in the hole filling area gray level image, an image formed by the enhanced gray level values of all the pixel points is recorded as an enhanced image of the hole filling area gray level image.
10. The method for metal paste wiring hole filling and monitoring for HTCC ceramic according to claim 1, wherein the step of judging whether the hole filling quality in the gray level image of the hole filling area is acceptable according to the enhanced image comprises the following specific steps:
dividing a defective region in the enhanced image by using the trained divided neural network, and judging that the filling quality in the gray level image of the filling region is unqualified when the defective region exists; and when the defect area does not exist, judging that the filling quality in the gray level image of the filling area is qualified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410281539.2A CN117876374B (en) | 2024-03-13 | 2024-03-13 | Metal slurry wiring hole filling and monitoring method for HTCC ceramic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410281539.2A CN117876374B (en) | 2024-03-13 | 2024-03-13 | Metal slurry wiring hole filling and monitoring method for HTCC ceramic |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117876374A true CN117876374A (en) | 2024-04-12 |
| CN117876374B CN117876374B (en) | 2024-05-28 |
Family
ID=90581506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410281539.2A Active CN117876374B (en) | 2024-03-13 | 2024-03-13 | Metal slurry wiring hole filling and monitoring method for HTCC ceramic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117876374B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210009032A (en) * | 2019-07-16 | 2021-01-26 | 홍범진 | Kit device for automatic truck car and control method |
| CN114998314A (en) * | 2022-07-18 | 2022-09-02 | 启东旺晟电子科技有限公司 | PCB (printed Circuit Board) defect detection method based on computer vision |
| CN115311270A (en) * | 2022-10-11 | 2022-11-08 | 南通至顺聚氨酯材料有限公司 | Plastic product surface defect detection method |
| CN115311301A (en) * | 2022-10-12 | 2022-11-08 | 江苏银生新能源科技有限公司 | PCB welding spot defect detection method |
| CN115311176A (en) * | 2022-10-12 | 2022-11-08 | 江苏菲尔浦物联网有限公司 | Night image enhancement method based on histogram equalization |
| CN116109644A (en) * | 2023-04-14 | 2023-05-12 | 东莞市佳超五金科技有限公司 | Surface defect detection method for copper-aluminum transfer bar |
| CN116205906A (en) * | 2023-04-25 | 2023-06-02 | 青岛豪迈电缆集团有限公司 | Nondestructive testing method for production abnormality in cable |
| CN117173158A (en) * | 2023-10-25 | 2023-12-05 | 深圳市德海威实业有限公司 | Intelligent detection method and system for quality of precise connector |
| CN117557566A (en) * | 2024-01-12 | 2024-02-13 | 深圳博上科技有限公司 | Intelligent detection method for quality of heating wire of electronic cigarette based on image characteristics |
-
2024
- 2024-03-13 CN CN202410281539.2A patent/CN117876374B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210009032A (en) * | 2019-07-16 | 2021-01-26 | 홍범진 | Kit device for automatic truck car and control method |
| CN114998314A (en) * | 2022-07-18 | 2022-09-02 | 启东旺晟电子科技有限公司 | PCB (printed Circuit Board) defect detection method based on computer vision |
| CN115311270A (en) * | 2022-10-11 | 2022-11-08 | 南通至顺聚氨酯材料有限公司 | Plastic product surface defect detection method |
| CN115311301A (en) * | 2022-10-12 | 2022-11-08 | 江苏银生新能源科技有限公司 | PCB welding spot defect detection method |
| CN115311176A (en) * | 2022-10-12 | 2022-11-08 | 江苏菲尔浦物联网有限公司 | Night image enhancement method based on histogram equalization |
| CN116109644A (en) * | 2023-04-14 | 2023-05-12 | 东莞市佳超五金科技有限公司 | Surface defect detection method for copper-aluminum transfer bar |
| CN116205906A (en) * | 2023-04-25 | 2023-06-02 | 青岛豪迈电缆集团有限公司 | Nondestructive testing method for production abnormality in cable |
| CN117173158A (en) * | 2023-10-25 | 2023-12-05 | 深圳市德海威实业有限公司 | Intelligent detection method and system for quality of precise connector |
| CN117557566A (en) * | 2024-01-12 | 2024-02-13 | 深圳博上科技有限公司 | Intelligent detection method for quality of heating wire of electronic cigarette based on image characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117876374B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114862862B (en) | Pump body cold shut defect identification method and system based on image processing | |
| CN113538429B (en) | Mechanical part surface defect detection method based on image processing | |
| CN114049489B (en) | Early warning method for breakage of optical fiber cable sheath | |
| CN108229550B (en) | Cloud picture classification method based on multi-granularity cascade forest network | |
| CN114897896B (en) | Building wood defect detection method based on gray level transformation | |
| CN116485785B (en) | Surface defect detection method for solar cell | |
| CN109255799B (en) | Target tracking method and system based on spatial adaptive correlation filter | |
| CN114494256A (en) | Electric wire production defect detection method based on image processing | |
| CN115908142A (en) | Contact net tiny part damage testing method based on visual recognition | |
| CN117541582B (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN117745715B (en) | Large-caliber telescope lens defect detection method based on artificial intelligence | |
| CN117876374B (en) | Metal slurry wiring hole filling and monitoring method for HTCC ceramic | |
| CN117078678B (en) | Waste silicon wafer shape detection method based on image recognition | |
| CN116681696B (en) | Mold quality monitoring method for automatic production equipment | |
| CN115841600B (en) | Deep learning-based sweet potato appearance quality classification method | |
| CN116664567A (en) | Solid insulation switch cabinet quality assessment method and system | |
| CN114663658B (en) | Small sample AOI surface defect detection method with cross-domain migration capability | |
| CN113643312B (en) | Cloud layer segmentation method based on true color satellite cloud picture and image processing | |
| CN113759148B (en) | Semiconductor image measuring method for artificial intelligent identification | |
| CN113643245A (en) | Screen defect measuring method and device and computer readable storage medium | |
| CN117593651B (en) | Tunnel crack segmentation recognition method | |
| CN117522868B (en) | Visual inspection method for production quality of welded pipe | |
| CN116563275B (en) | Method for detecting internal defects of crystalline silicon battery | |
| CN117974657B (en) | Cable surface defect detection method based on computer vision | |
| CN117876379B (en) | Intelligent anchor rod defect detection method based on image characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |